---
title: "Anthropic Claude Fine-Tuning Patterns on Amazon Bedrock (2026)"
description: "Anthropic still does not expose fine-tuning through its public API in 2026 — Claude Haiku SFT lives exclusively on Amazon Bedrock (us-west-2). We document the JSONL format, system-message rules, the 4-tier constitution priorities Claude inherits, and when Bedrock SFT beats prompt caching."
canonical: https://callsphere.ai/blog/vw8g-anthropic-claude-fine-tuning-patterns-bedrock-2026
category: "AI Engineering"
tags: ["Fine-Tuning", "Anthropic", "Claude", "Bedrock", "AWS"]
author: "CallSphere Team"
published: 2026-03-17T00:00:00.000Z
updated: 2026-05-07T22:23:10.884Z
---

# Anthropic Claude Fine-Tuning Patterns on Amazon Bedrock (2026)

> Anthropic still does not expose fine-tuning through its public API in 2026 — Claude Haiku SFT lives exclusively on Amazon Bedrock (us-west-2). We document the JSONL format, system-message rules, the 4-tier constitution priorities Claude inherits, and when Bedrock SFT beats prompt caching.

> **TL;DR** — Anthropic does not let you fine-tune Claude via its public API. The only supported path in 2026 is **Claude 3 Haiku SFT on Amazon Bedrock** in us-west-2. Use it for narrow, latency-sensitive verticals where Haiku's $0.25/$1.25 per 1M tokens beats Sonnet/Opus and prompt caching alone is not enough.

## What it does

Bedrock SFT teaches Claude 3 Haiku domain-specific style, classification labels, and tool-call shapes. Anthropic's January 2026 constitution refresh hardcodes a **4-tier priority hierarchy** (safety → ethics → compliance → helpfulness) that fine-tuning **cannot override** — your training data is layered on top of that prior, not under it.

For Sonnet 4.x, Opus 4.7, and any model post-Haiku 3, fine-tuning is **not available**. Anthropic's official position: lean on **prompt caching** (90% discount on cached system prompts), **extended thinking**, and **memory tools** instead.

## How it works

1. Format JSONL: each line has an optional `system` message + an alternating `user` → `assistant` array (must start with user, end with assistant, ≥ 2 messages).
2. Upload to S3 in us-west-2.
3. Create a Bedrock customization job referencing `anthropic.claude-3-haiku-20240307-v1:0`.
4. Provision throughput on the resulting custom model (Bedrock requires Provisioned Throughput for fine-tuned Claudes — no on-demand inference).
5. Hit the new model ARN exactly like any other Bedrock invoke.

```mermaid
flowchart LR
  S3[(S3 train.jsonl)] --> JOB[Bedrock SFT job]
  JOB --> CKPT[Custom Haiku checkpoint]
  CKPT --> PT[Provisioned Throughput unit]
  PT --> APP[Agent runtime]
  APP -->|invoke_model| PT
```

## CallSphere implementation

We mostly **don't** fine-tune Claude. CallSphere ships **37 agents** across **6 verticals** powered by Claude Sonnet 4.6 + GPT-4o + Gemini 2.5 — orchestrated through our own router. The Healthcare post-call analytics path uses **gpt-4o-mini** (cheaper, fine-tunable). For deep reasoning we lean on **prompt caching** (Anthropic's 90% cached-token discount on a 12k system prompt saves us ~$3,800/mo at Scale-tier volume) rather than custom Haiku, because cache hits beat custom-throughput costs at our QPS.

When a buyer needs Claude SFT (regulated insurance routing, e.g.), we provision on Bedrock and bill it through the **Scale plan ($1,499/mo)** with a co-managed customization. **14-day trial** + **22% affiliate** still apply.

## Build steps with code

```python
import boto3
br = boto3.client("bedrock", region_name="us-west-2")

br.create_model_customization_job(
    customizationType="FINE_TUNING",
    baseModelIdentifier="anthropic.claude-3-haiku-20240307-v1:0",
    jobName="callsphere-claim-router-v3",
    customModelName="claude-haiku-claim-router",
    trainingDataConfig={"s3Uri":"s3://cs-sft/claims/train.jsonl"},
    validationDataConfig={"validators":[{"s3Uri":"s3://cs-sft/claims/val.jsonl"}]},
    hyperParameters={"epochCount":"2","batchSize":"32",
                     "learningRate":"0.00001","learningRateWarmupSteps":"50"},
    outputDataConfig={"s3Uri":"s3://cs-sft/claims/out/"},
)
```

```json
{"system":"You are a claims router.",
 "messages":[
   {"role":"user","content":"Patient stage IV, denied prior auth, plan United"},
   {"role":"assistant","content":"ROUTE: appeals_specialist\nRATIONALE: oncology + denied PA"}
 ]}
```

## Pitfalls

- **Region lock-in** — only us-west-2. If your data has residency rules, this is a blocker.
- **Provisioned Throughput is expensive** — minimum ~$50/hr for one model unit; under ~80 RPS sustained, prompt caching wins on cost.
- **No Sonnet/Opus SFT** — don't promise customers Sonnet customization; it doesn't exist.
- **Constitutional priors win** — even with SFT, Claude will refuse outputs that violate its 4-tier constitution.

## FAQ

**Q: Can I fine-tune Claude through claude.ai or the public API?**
No. Only via Amazon Bedrock as of May 2026.

**Q: How much data do I need?**
Anthropic's docs suggest 50–10,000 examples; in our experience, narrow classification works at 200–500.

**Q: Is prompt caching always better?**
At low QPS yes. Above ~80 sustained RPS where Provisioned Throughput is fully utilized, custom Haiku catches up.

**Q: What about distilling Sonnet → Haiku?**
You can generate Sonnet outputs, store them, and use those as your Haiku SFT corpus. Anthropic's TOS allows it for your own internal models.

**Q: Does fine-tuning weaken Claude's safety?**
The 2026 constitution refresh is enforced at runtime — SFT cannot remove safety refusals.

## Sources

- [Anthropic — Fine-Tune Claude 3 Haiku in Amazon Bedrock](https://www.anthropic.com/news/fine-tune-claude-3-haiku)
- [AWS — Fine-Tune Claude 3 Haiku Blog](https://aws.amazon.com/blogs/machine-learning/fine-tune-anthropics-claude-3-haiku-in-amazon-bedrock-to-boost-model-accuracy-and-quality/)
- [Anthropic Cookbook — Bedrock Fine-Tuning](https://platform.claude.com/cookbook/finetuning-finetuning-on-bedrock)
- [TechCrunch — Anthropic Revises Claude's Constitution (Jan 2026)](https://techcrunch.com/2026/01/21/anthropic-revises-claudes-constitution-and-hints-at-chatbot-consciousness/)

---

Source: https://callsphere.ai/blog/vw8g-anthropic-claude-fine-tuning-patterns-bedrock-2026